Product Information

Shrutlekhan-Advance

Real-time dictation powered by AI, tailored for Indic languages

Brief Description

Shrutlekhan-Advance is a state-of-the-art, general-purpose continuous automatic speech recognition (ASR) system designed for Indian languages. It accurately transcribes spoken words into text, making it an invaluable tool for a wide range of applications. The system employs an end-to-end AI-driven approach, mapping audio inputs directly to text outputs using deep learning algorithms to ensure precise and reliable transcription.



Use Cases

  • Voice-Driven Content Creation: Individuals efficiently create content such as emails, blogs, books, and other written materials by voice dictation, enhancing productivity and accessibility in writing tasks.
  • Judicial and Legal Documentation: Transcribe courtroom proceedings, judgments, and daily orders.
  • Media and Journalism: Convert interviews, news coverage, and panel discussions into publishable text.
  • Education and Research: Record and transcribe lectures, seminars, and oral histories.
  • Corporate Communication: Document business meetings, voice memos, and client calls.
  • Government and Administrative Workflows: Enable digital transformation with accurate voice-to-text transcription.

Salient Features

  • Real-Time Online Transcription: High-speed, high-accuracy transcription of live speech.
  • Seamless Integration: Easy API-based integration with existing systems and workflows.
  • Instant and Precise Text Creation: Automatically generate and structure text from audio inputs.
  • Voice-Based Editing & Formatting: Control text formatting and editing using voice commands.
  • Audio File Transcription Support: Upload and transcribe pre-recorded audio content with ease.

Technical Specifications

  • Supported Languages: Indian languages (Hindi, Marathi, Kannada, Tamil, Indian English, Gujarati) 
  • Model Architecture: End-to-End Conformer (Encoder-Decoder with Attention/CTC) Architecture
  • Input Types: Live Microphone Audio, Pre-recorded Audio Files (WAV, MP3, FLAC, etc.)
  • Output Formats: Editable Transcripts
  • Deployment Modes: Web-based Interface, REST APIs, On-Premise Option

Contact Details

Mahesh Bhargava

Scientist E

Multilingual Technologies Group,

C-DAC Pune.

Phone: 02025503305

Email: mbhargava[at]cdac[dot]in

Top